Causal Algorithmic Fairness and Transparency - Naver Labs Europe
loader image

blankSeminars at NAVER LABS Europe are open to the public. This seminar is virtual and requires registration. Registration link.

Date: 30th September 2020, 5:00 PM – 6:00 PM CEST

Causal Algorithmic Fairness and Transparency

Speaker: Babak Salimi is an Assistant Professor in HDSI at UC San Diego. Before joining UC San Diego, he was a Postdoctoral Research Associate in the Department of Computer Science and Engineering, University of Washington, where he worked with Professor Dan Suciu and the Database group. He received his PhD from the School of Computer Science at Carleton University, advised by Professor Leopoldo Bertossi. His research seeks to unify techniques from theoretical data management, causal inference and machine learning to develop a new generation of decision-support systems that help people with heterogeneous background to interpret data. His ongoing work in causal relational learning aims to develop the necessary conceptual foundations to make causal inference from complex relational data. Further, his research in the area of responsible data science develops needed foundations for ensuring fairness and accountability in the era of data-driven decisions. His research contributions have been recognized with a Postdoc Research Award at University of Washington, a Best Demonstration Paper Award at VLDB 2018, a Best Paper Award at SIGMOD 2019 and a Research Highlight Award at  SIGMOD 2020.

Scaling and democratizing access to big data promises to provide meaningful and actionable information that supports decision-making. Today, data-driven decisions profoundly affect the course of our lives, such as whether to admit applicants to a particular school, offer them a job, or grant them a mortgage. Unfair, inconsistent, or faulty decision-making raises serious concerns about ethics and responsibility. For example, we may know that our training data is biased, but how do we avoid propagating discrimination when we use this data?  How do we avoid incorrect, spurious and non-reproducible findings?  How can we curate and expose existing data to make it “safe” for informed decision-making? In this talk, I describe how we can combine techniques from causal inference and data management to develop systems and algorithms that help answer questions about fairness and transparency.  First, I present a new notion of fairness that subsumes and improves upon previous definitions and correctly distinguishes between fairness violations and non-violations. Further, I discuss how we can leverage techniques from data management to remove historical discrimination from data. Second I present a novel declarative framework that enables reasoning about fairness and discrimination from complex relational data. Finally, I present my ongoing projects that use counterfactual reasoning and provenance for explaining black-box decision-making algorithms.

Ceci correspond à une petite biographie d'environ 200 caractéres